Dear all,

I use the generalized linear model module to estimate a Poisson regression

in SPSS. (Potential) problem: The data represent an interrupted time series

(one country, 30 observations). Is it possible to adjust the standard errors

for the fact that the observations won't be independent - if so, how could

this be done in SPSS?

As an alternative, I thougt about using an autoregressive model (including

the predictors at t-1), but I am not sure whether this would yield adequate

standard errors?

Best, N.

--

Sent from:

http://spssx-discussion.1045642.n5.nabble.com/=====================

To manage your subscription to SPSSX-L, send a message to

[hidden email] (not to SPSSX-L), with no body text except the

command. To leave the list, send the command

SIGNOFF SPSSX-L

For a list of commands to manage subscriptions, send the command

INFO REFCARD